diff options
Diffstat (limited to 'bench/perf_monitoring/gemm/changesets.txt')
| -rw-r--r-- | bench/perf_monitoring/gemm/changesets.txt | 21 |
1 files changed, 13 insertions, 8 deletions
diff --git a/bench/perf_monitoring/gemm/changesets.txt b/bench/perf_monitoring/gemm/changesets.txt index 4bff3cc4a..9a2336390 100644 --- a/bench/perf_monitoring/gemm/changesets.txt +++ b/bench/perf_monitoring/gemm/changesets.txt @@ -25,13 +25,13 @@ before-evaluators #6742:0cbd6195e829 # merge default to tensors #6747:853d2bafeb8f # Generalized the gebp apis 6765:71584fd55762 # Made the blocking computation aware of the l3 cache; Also optimized the blocking parameters to take into account the number of threads used for a computation -#6781:9cc5a931b2c6 # generalized gemv -#6792:f6e1daab600a # ensured that contractions that can be reduced to a matrix vector product +6781:9cc5a931b2c6 # generalized gemv +6792:f6e1daab600a # ensured that contractions that can be reduced to a matrix vector product #6844:039efd86b75c # merge tensor 6845:7333ed40c6ef # change prefetching in gebp #6856:b5be5e10eb7f # merge index conversion -#6893:c3a64aba7c70 # clean blocking size computation -#6898:6fb31ebe6492 # rotating kernel for ARM +6893:c3a64aba7c70 # clean blocking size computation +6898:6fb31ebe6492 # rotating kernel for ARM 6899:877facace746 # rotating kernel for ARM only #6904:c250623ae9fa # result_of 6921:915f1b1fc158 # fix prefetching change for ARM @@ -50,7 +50,7 @@ before-evaluators 7098:b6f1db9cf9ec # Bug 992: don't select a 3p GEMM path with non-vectorizable scalar types, this hits unsupported paths in symm/triangular products code 7591:09a8e2186610 # 3.3-alpha1 7650:b0f3c8f43025 # help clang inlining -#8744:74b789ada92a # Improved the matrix multiplication blocking in the case where mr is not a power of 2 (e.g on Haswell CPUs) +8744:74b789ada92a # Improved the matrix multiplication blocking in the case where mr is not a power of 2 (e.g on Haswell CPUs) 8789:efcb912e4356 # Made the index type a template parameter to evaluateProductBlockingSizes. Use numext::mini and numext::maxi instead of std::min/std::max to compute blocking sizes 8972:81d53c711775 # Don't optimize the processing of the last rows of a matrix matrix product in cases that violate the assumptions made by the optimized code path 8985:d935df21a082 # Remove the rotating kernel. @@ -59,6 +59,11 @@ before-evaluators 9174:d228bc282ac9 # merge 9212:c90098affa7b # Fix performance regression introduced in changeset 8aad8f35c955 9213:9f1c14e4694b # Fix performance regression in dgemm introduced by changeset 81d53c711775 -3.3-beta2 -3.3-rc1 -3.3.0 +9361:69d418c06999 # 3.3-beta2 +9583:bef509908b9d # 3.3-rc1 +9792:26667be4f70b # 3.3.0 +9942:b1d3eba60130 # Operators += and -= do not resize! +9943:79bb9887afd4 # Ease compiler job to generate clean and efficient code in mat*vec +9946:2213991340ea # Complete rewrite of column-major-matrix * vector product to deliver higher performance of modern CPU. +9953:21acc0e8d782 # Improve performance of row-major-dense-matrix * vector products for recent CPUs. + |